Abstract
In this paper, we study the problem of question answering over knowledge base. We identify that the primary bottleneck in this problem is the difficulty in accurately predicting the relations connecting the subject entity to the object entities. We advocate a new model architecture, APVA, which includes a verification mechanism responsible for checking the correctness of predicted relations. The APVA framework naturally supports a well-principled iterative training procedure, which we call turbo training. We demonstrate via experiments that the APVA-TUBRO approach drastically improves the question answering performance.- Anthology ID:
- C18-1170
- Volume:
- Proceedings of the 27th International Conference on Computational Linguistics
- Month:
- August
- Year:
- 2018
- Address:
- Santa Fe, New Mexico, USA
- Editors:
- Emily M. Bender, Leon Derczynski, Pierre Isabelle
- Venue:
- COLING
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1998–2009
- Language:
- URL:
- https://aclanthology.org/C18-1170
- DOI:
- Cite (ACL):
- Yue Wang, Richong Zhang, Cheng Xu, and Yongyi Mao. 2018. The APVA-TURBO Approach To Question Answering in Knowledge Base. In Proceedings of the 27th International Conference on Computational Linguistics, pages 1998–2009, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
- Cite (Informal):
- The APVA-TURBO Approach To Question Answering in Knowledge Base (Wang et al., COLING 2018)
- PDF:
- https://preview.aclanthology.org/fix-dup-bibkey/C18-1170.pdf
- Data
- SimpleQuestions